Study on Prediction Method for Accident Parameters of Lead-bismuth Reactor Based on Coupling Multivariable LSTM and Optimization Algorithm

Ji Nan; Yang Junkang; Zhao Pengcheng; Wang Kai

doi:10.13832/j.jnpe.2023.05.0064

Volume 44 Issue 5

Oct. 2023

Turn off MathJax

Article Contents

Article Navigation > Nuclear Power Engineering > 2023 > 44(5): 64-70

Ji Nan, Yang Junkang, Zhao Pengcheng, Wang Kai. Study on Prediction Method for Accident Parameters of Lead-bismuth Reactor Based on Coupling Multivariable LSTM and Optimization Algorithm[J]. Nuclear Power Engineering, 2023, 44(5): 64-70. doi: 10.13832/j.jnpe.2023.05.0064

Citation:

Ji Nan, Yang Junkang, Zhao Pengcheng, Wang Kai. Study on Prediction Method for Accident Parameters of Lead-bismuth Reactor Based on Coupling Multivariable LSTM and Optimization Algorithm[J]. Nuclear Power Engineering, 2023, 44(5): 64-70. doi: 10.13832/j.jnpe.2023.05.0064

Citation:

Ji Nan, Yang Junkang, Zhao Pengcheng, Wang Kai. Study on Prediction Method for Accident Parameters of Lead-bismuth Reactor Based on Coupling Multivariable LSTM and Optimization Algorithm[J]. Nuclear Power Engineering, 2023, 44(5): 64-70. doi: 10.13832/j.jnpe.2023.05.0064

PDF( 3132 KB)

Study on Prediction Method for Accident Parameters of Lead-bismuth Reactor Based on Coupling Multivariable LSTM and Optimization Algorithm

doi: 10.13832/j.jnpe.2023.05.0064

School of Nuclear Science and Technology, University of South China, Hengyang, Hunan, 421001, China

Received Date: 2022-10-14
Rev Recd Date: 2022-12-02
Publish Date: 2023-10-13

Abstract

Abstract

Accurate prediction of key parameters of lead-bismuth reactor under accident conditions is an important content of reactor safety analysis, which is of great significance to improve the safety of the reactor under accident conditions. In this work, an optimization algorithm is used to improve the prediction performance of the Long Short Term Memory (LSTM) neural network by hyperparameter optimization, and a parameter prediction method based on the coupled optimization algorithm of multivariate LSTM neural network is proposed. For the parameter prediction problem of lead-bismuth fast reactor MARS-3 under unprotected loss of flow accident conditions, a comprehensive evaluation of the proposed method is performed using Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method after data samples generated by the sub-channel code SUBCHANFLOW. The results show that the prediction performance of the multivariate LSTM neural network coupled with the Particle Swarm optimization method is optimal, and its computational efficiency can be improved to 438 times that of SUBCHANFLOW. The relevant research results can help improve the efficiency of predicting key thermal parameters of lead-bismuth reactors and improve the emergency response capability of lead-bismuth reactors.
- Multivariable long short term memory (LSTM),
- Optimal algorithm,
- Lead bismuth reactor,
- Accident parameters prediction,
- SUBCHANFLOW

FullText(HTML)

References(24)

References

[1]	LORUSSO P, BASSINI S, DEL NEVO A, et al. GEN-IV LFR development: status & perspectives[J]. Progress in Nuclear Energy, 2018, 105: 318-331. doi: 10.1016/j.pnucene.2018.02.005
[2]	辜峙钘, 王刚, 汪振, 等. 10MW_th铅铋冷却快堆无保护失流合并失热阱瞬态分析[C]//第十四届全国反应堆热工流体学术会议暨中核核反应堆热工水力技术重点实验室2015年度学术年会论文集. 北京: 清华大学先进反应堆工程与安全教育部重点实验室, 2015.
[3]	张思原,卢忝余,曾辉,等. 基于LSTM的核电传感器多特征融合多步状态预测[J]. 核动力工程,2021, 42(4): 208-213.
[4]	王东东,杨红义,王端,等. 中国实验快堆热工参数的自适应BP神经网络预测方法研究[J]. 原子能科学技术,2020, 54(10): 1809-1816.
[5]	吴天昊,栾秀春,王俊玲,等. 核反应堆功率模糊广义预测控制[J]. 核科学与工程,2016, 36(3): 299-305. doi: 10.3969/j.issn.0258-0918.2016.03.001
[6]	蒋波涛,黄新波,WESLEY H J,等. 基于ν-支持向量机的事故工况下反应堆功率预测[J]. 核动力工程,2019, 40(6): 105-108.
[7]	孙虹洁,赵振华,黄林显,等. 多变量LSTM神经网络模型在地下水位预测中的应用[J]. 人民黄河,2022, 44(8): 69-75. doi: 10.3969/j.issn.1000-1379.2022.08.014
[8]	孙原理,宋志浩. 基于卷积长短期记忆网络和人工鲸鱼算法的核反应堆运行事件诊断方法研究[J]. 核动力工程,2022, 43(4): 185-190.
[9]	闫佰忠,孙剑,王昕洲,等. 基于多变量LSTM神经网络的地下水水位预测[J]. 吉林大学学报:地球科学版,2020, 50(1): 208-216.
[10]	LEE D, SEONG P H, KIM J. Autonomous operation algorithm for safety systems of nuclear power plants by using long-short term memory and function-based hierarchical framework[J]. Annals of Nuclear Energy, 2018, 119: 287-299. doi: 10.1016/j.anucene.2018.05.020
[11]	杨敏雪,于斐,王培生,等. 基于ARIMA和LSTM神经网络的乌鲁木齐市乙型肝炎发病预测研究[J]. 现代预防医学,2022, 49(16): 2903-2907.
[12]	雷萌,吕游,魏玮,等. 基于LSTM神经网络与贝叶斯优化的电站风机故障预警[J]. 热能动力工程,2022, 37(8): 213-220.
[13]	孙燕成,陈富安. 基于PSO优化LSTM神经网络的机械臂逆运动学求解研究[J]. 电子测量技术,2022, 45(13): 40-45.
[14]	刘东,罗琦,唐雷,等. 基于PINN深度机器学习技术求解多维中子学扩散方程[J]. 核动力工程,2022, 43(2): 1-8.
[15]	CLERC M. Particle swarm optimization[M]. UK: ISTE, 2006: 93.
[16]	MIRJALILI S. Genetic algorithm[M]//MIRJALILI S. Evolutionary Algorithms and Neural Networks. Cham: Springer, 2019: 43-55.
[17]	WANG H X, LIU J Y, ZHI J, et al. The improvement of quantum genetic algorithm and its application on function optimization[J]. Mathematical Problems in Engineering, 2013, 2013: 730749.
[18]	MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67. doi: 10.1016/j.advengsoft.2016.01.008
[19]	王晓辉,邓威威,齐旺. 基于超参数优化的短期电力负荷预测模型[J]. 国外电子测量技术,2022, 41(6): 152-158. doi: 10.19652/j.cnki.femt.2103537
[20]	韩超. 一种基于改进PSO优化的LSTM航迹预测模型[J]. 舰船电子工程,2022, 42(8): 120-124,154. doi: 10.3969/j.issn.1672-9730.2022.08.025
[21]	高超,孙谊媊,赵洪峰,等. 改进的黑猩猩算法优化LSTM的短期电力负荷预测[J]. 现代电子技术,2022, 45(21): 122-126.
[22]	JING T, JUNG Y S, YANG W S. Stationary liquid fuel fast reactor SLFFR — Part II: safety analysis[J]. Nuclear Engineering and Design, 2016, 310: 493-506. doi: 10.1016/j.nucengdes.2016.10.023
[23]	张一帆,刘宙宇,曹良志,等. 小型铅铋冷却快堆瞬态安全分析[J]. 原子能科学技术,2020, 54(11): 2081-2088.
[24]	江磊,张佑印,张景全,等. 基于熵权-TOPSIS法的省域休闲体育竞争力评价及差异特征分析[J]. 陕西师范大学学报:自然科学版,2022, 50(6): 113-123.